XS-VID: An Extremely Small Video Object Detection Benchmark

XS-VID is a benchmark dataset designed to evaluate video object detection models, particularly focusing on efficiency and effectiveness in resource-limited situations. The dataset includes a variety of videos and scenarios to assess model capabilities. It was created by lanlanlan23 and last updated on March 20, 2025.

Use Cases

• Benchmarking model performance on extremely small objects based on the dataset's stated focus
• Evaluating detection efficiency in resource-limited situations based on the description
• Testing model generalization across a variety of video scenarios mentioned in the description

Strengths

• Designed specifically for the challenging task of extremely small video object detection
• Includes a variety of videos and scenarios to assess model capabilities

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Dataset size and file formats are unknown

Provenance

Source

huggingface

Freshness

Last updated 2025-03-20 03:09:53